5
●330
pip install selenium pandas googletrans==4.0.0-rc1 undetected-chromedriver
import time
import pandas as pd
from googletrans import Translator
from selenium import webdriver
from selenium.webdriver.common.by import By
import undetected_chromedriver as uc
# Tarayıcı ve çevirmen başlat
options = uc.ChromeOptions()
options.add_argument("--no-sandbox")
options.add_argument("--disable-dev-shm-usage")
driver = uc.Chrome(options=options)
translator = Translator()
# Yorum verilerini çek
def scrape_reviews(booking_url, max_pages=3):
all_reviews = []
driver.get(booking_url)
time.sleep(5) # Sayfanın yüklenmesini bekle
for page in range(max_pages):
print(f"--- Sayfa {page+1} ---")
time.sleep(2)
reviews = driver.find_elements(By.CLASS_NAME, 'review_list_new_item_block')
for r in reviews:
try:
name = r.find_element(By.CLASS_NAME, 'bui-avatar-block__title').text.strip()
nationality = r.find_element(By.CLASS_NAME, 'bui-avatar-block__subtitle').text.strip()
score = r.find_element(By.CLASS_NAME, 'bui-review-score__badge').text.strip()
date = r.find_element(By.CLASS_NAME, 'c-review-block__date').text.strip()
try:
stay_info = r.find_element(By.CLASS_NAME, 'c-review-block__stay-date').text.strip()
except:
stay_info = ''
review_parts = r.find_elements(By.CLASS_NAME, 'c-review__body')
review_text = ' '.join([p.text.strip() for p in review_parts if p.text.strip()])
# Otomatik çeviri
detected = translator.detect(review_text).lang
if detected != "en":
review_en = translator.translate(review_text, dest='en').text
else:
review_en = review_text
all_reviews.append({
'Name': name,
'Nationality': nationality,
'Score': score,
'Date': date,
'Stay Info': stay_info,
'Review Original': review_text,
'Review (EN)': review_en
})
except Exception as e:
print(f"Yorum parse hatası: {e}")
continue
# Sonraki sayfaya geç
try:
next_btn = driver.find_element(By.CSS_SELECTOR, 'a.pagenext')
driver.execute_script("arguments[0].click();", next_btn)
except:
print("Daha fazla sayfa yok.")
break
return all_reviewsif __name__ == "__main__":
# Örnek Booking yorum sayfası (bir otelin yorum sekmesiyle biten URL)
url = "https://www.booking.com/hotel/fr/example.tr.html#tab-reviews" # Gerçek URL ile değiştir
yorumlar = scrape_reviews(url, max_pages=5)
df = pd.DataFrame(yorumlar)
df.to_csv("booking_yorumlar.csv", index=False, encoding='utf-8-sig')
print("Yorumlar başarıyla CSV'ye kaydedildi.")
driver.quit() 
